Complex-valued Neural Networks -- Theory and Analysis
Complex-valued neural networks (CVNNs) have recently been successful in various pioneering areas which involve wave-typed information and frequency-domain processing. This work addresses different...
Performance Analysis of LOS THz Systems under Misalignment and Deterministic Fading
Line-of-sight (LOS) wireless communication at terahertz (THz) frequency bands is envisioned to play a major role in defining next-generation wireless technologies. This work analyzes the...
Minimizing the Hidden Cost of Scales: Graph-Guided Ultra-Low-Bit Quantization for Large Language Models
Post-training quantization (PTQ) is critical for the efficient deployment of large language models (LLMs). Recent ultra-low-bit PTQ methods rely on rigid weight-saliency assumptions or position...
Bi-VLM: Pushing Ultra-Low Precision Post-Training Quantization Boundaries in Vision-Language Models
We address the critical gap between the computational demands of vision-language models and the possible ultra-low-bit weight precision (bitwidth $\leq2$ bits) we can use for higher efficiency....